SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.08473 · NeurIPS · 2020

Certifiably Adversarially Robust Detection of Out-of-Distribution Data

Matthias Hein, Julian Bitterwolf, Alexander Meinke

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep neural networks are known to be overconfident when applied to out-ofdistribution (OOD) inputs which clearly do not belong to any class. This is a problem in safety-critical applications since a reliable assessment of the uncertainty of a classifier is a key property, allowing the system to trigger human intervention or to transfer into a safe state. In this paper, we aim for certifiable worst case guarantees for OOD detection by enforcing not only low confidence at the OOD point but also in an l ∞ -ball around it. For this purpose, we use interval bound propagation (IBP) to upper bound the maximal confidence in the l ∞ -ball and minimize this upper bound during training time. We show that non-trivial bounds on the confidence for OOD data generalizing beyond the OOD dataset seen at training time are possible. Moreover, in contrast to certified adversarial robustness which typically comes with significant loss in prediction performance, certified guarantees for worst case OOD detection are possible without much loss in accuracy.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2007.08473")
get_code_for_paper("2007.08473")
have("2007.08473")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2007.08473.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2007.08473.svg)](https://syntology.ai/paper/2007.08473)

Connect an agent — have() is free.